Video Prediction On Kth

评估指标

Cond

FVD

LPIPS

PSNR

Params (M)

Pred

SSIM

Train

评测结果

各个模型在此基准测试上的表现结果

									Paper Title	Repository
WAM	10	-	-	29.85	-	20	0.893	-	Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction
SRVP	10	222 ± 3	0.0736±0.0029	29.69±032	-	30	0.8697±0.0046	10	Stochastic Latent Residual Video Prediction
SLAMP	10	228 ± 5	0.0795±0.0034	29.39±0.30	-	30	0.8646±0.0050	10	SLAMP: Stochastic Latent Appearance and Motion Prediction
E3d-LSTM	10	-	-	29.31	-	20	0.879	-	Eidetic 3D LSTM: A Model for Video Prediction and Beyond	-
VarNet	10	-	-	28.48	-	20	0.843	-	VarNet: Exploring Variations for Unsupervised Video Prediction	-
PredRNN++	10	-	-	28.47	-	20	0.865	-	PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
PredRNN-V2	10	-	0.139	28.37	-	20	0.839	-	PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
SV2P (from SRVP)	10	636 ± 1	0.2049±0.0053	28.19±0.31	-	30	0.838	10	Stochastic Variational Video Prediction
SVG-LP (from SRVP)	10	377 ± 6	0.0923±0.0038	28.06±0.29	-	30	0.8438±0.0054	10	Stochastic Video Generation with a Learned Prior
MSPred	-	-	0.029	27.81	-	-	0.951	-	MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks
SAVP-VAE	10	-	-	27.77	-	20	0.852	-	Stochastic Adversarial Video Prediction
Conv-TT-LSTM	10	-	0.196	27.62	-	20	0.815	-	Convolutional Tensor-Train LSTM for Spatio-temporal Learning
Znet	10	-	-	27.58	-	20	0.817	-	Z-Order Recurrent Neural Networks for Video Prediction	-
LMC	10	-	159.8	27.5	-	40	0.879	-	Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning
DFN	10	-	-	27.26	-	20	0.794	-	Dynamic Filter Networks
Grid-keypoints	10	144.2	0.092	27.11	2.0	40	0.837	10	Accurate Grid Keypoint Learning for Efficient Video Prediction
MSNET	10	-	-	27.08	-	20	0.876	-	Mutual Suppression Network for Video Prediction using Disentangled Features	-
TrajGRU	10	-	-	26.97	-	20	0.790	-	Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
SAVP (from SRVP)	10	374 ± 3	0.1120±0.0039	26.51±0.29	-	30	0.7564±0.0062	10	Stochastic Adversarial Video Prediction
MCnet + Residual	10	-	-	26.29	-	20	0.806	-	Decomposing Motion and Content for Natural Video Sequence Prediction

0 of 31 row(s) selected.